RaBiT

Reported on 6 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical6 results

Medical Image SegmentationonBKAI-IGH NeoPolyp-Small
Average Dice· 2023-07-12
0.94
SOTA
RaBiT: An Efficient Transformer using Bidirectional Feature Pyramid Network with Reverse Attention for Colon Polyp Segmentation arXiv:2307.06420
Medical Image SegmentationonBKAI-IGH NeoPolyp-Small
mIoU· 2023-07-12
0.886
SOTA
RaBiT: An Efficient Transformer using Bidirectional Feature Pyramid Network with Reverse Attention for Colon Polyp Segmentation arXiv:2307.06420
Medical Image SegmentationonKvasir-SEG
mIoU· 2023-07-12
0.873
best: 0.9065 (EffiSegNet-B5)
RaBiT: An Efficient Transformer using Bidirectional Feature Pyramid Network with Reverse Attention for Colon Polyp Segmentation arXiv:2307.06420
Medical Image SegmentationonKvasir-SEG
mean Dice· 2023-07-12
0.927
best: 0.9502 (DUCK-Net)
RaBiT: An Efficient Transformer using Bidirectional Feature Pyramid Network with Reverse Attention for Colon Polyp Segmentation arXiv:2307.06420
Medical Image SegmentationonCVC-ClinicDB
mIoU· 2023-07-12
0.911
best: 0.9343 (DUCK-Net)
RaBiT: An Efficient Transformer using Bidirectional Feature Pyramid Network with Reverse Attention for Colon Polyp Segmentation arXiv:2307.06420
Medical Image SegmentationonCVC-ClinicDB
mean Dice· 2023-07-12
0.951
best: 0.9684 (DUCK-Net)
RaBiT: An Efficient Transformer using Bidirectional Feature Pyramid Network with Reverse Attention for Colon Polyp Segmentation arXiv:2307.06420